SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.08813 · 2020

Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

5 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 2 failures of our instrument; 8 no recorded run), measured 2026-11-21; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2003.08813.json · badge: /api/ran/2003.08813.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
luogen1996/MCN canonical (classifier label)
classifier basis: census
5 ran · 8 no recorded run
FunctionStatusWhere it lives
bert_output_sum Ran
ran on a synthesized input
luogen1996/MCN/model/bert.py
code served (permissive licence) · get_code("2c78556cd9635a1d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 1, dtype family float, shape (768,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function bert_output_sum takes a single parameter 'o' and slices it into 4 chunks
# of size 768 each, then sums them together.
# o needs to be a tensor of shape (768*4,) = (3072,)

o = torch.randn(3072)

ARGS = {
    "o": o
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (768,) — shape (768,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_from_dict Ran
ran on a synthesized input
luogen1996/MCN/utils/parse_config.py
code served (permissive licence) · get_code("136643a1b2ec6aa9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned CfgNode. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from yacs.config import CfgNode as CN

torch_seed = 0

# Create test dictionary to merge
test_dict = {
    "learning_rate": 0.001,
    "batch_size": 32,
    "hidden_dim": 128,
}

# Create base config
base_cfg = CN()
base_cfg.model = CN()
base_cfg.model.type = "resnet"

# Create prefix for nested access
prefix = "model.training"

ARGS = {
    "dct": test_dict,
    "prefix": prefix,
    "cfg": base_cfg,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yacs — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CfgNode — a CfgNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CfgNode output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_checkpoint_paths Ran
ran; our contract draft was wrong, not the code
luogen1996/MCN/model/bert.py
code served (permissive licence) · get_code("73debbc8d76d4ded")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned CheckpointPaths. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
from collections import namedtuple

# Create a temporary directory to serve as model_path
temp_dir = tempfile.mkdtemp()

# The function expects a model_path directory
# It will construct paths to config, checkpoint, and vocab files
# The function doesn't actually read these files, just constructs the paths
model_path = temp_dir

ARGS = {
    'model_path': model_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CheckpointPaths — a CheckpointPaths output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CheckpointPaths output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
letterbox_image Ran
ran; our contract draft was wrong, not the code
luogen1996/MCN/utils/utils.py
code served (permissive licence) · get_code("fe7e8a0ae28d05e2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Image. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

from PIL import Image

# Create a small test image
image = Image.new('RGB', (100, 80), color=(200, 100, 50))

# Define target size for letterboxing
size = (128, 128)

ARGS = {
    'image': image,
    'size': size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rand Ran
ran, honoured the contract we drafted
luogen1996/MCN/utils/utils.py
code served (permissive licence) · get_code("cdf3547dcf481932")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "a": 0,
    "b": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
aspp_decoder Not yet run
unverified (harvested, no recorded run)
luogen1996/MCN/model/mcn_model.py
code served (permissive licence) · get_code("91dce3275884c301")
How it ran

no invocation recorded.

expand_and_tile Not yet run
unverified (harvested, no recorded run)
luogen1996/MCN/model/utils.py
code served (permissive licence) · get_code("47337bf91f204990")
How it ran

no invocation recorded.

expand_and_tile_1 Not yet run
unverified (harvested, no recorded run)
luogen1996/MCN/model/utils.py
code served (permissive licence) · get_code("a6d7706f7a9a3eca")
How it ran

no invocation recorded.

global_attention_block Not yet run
unverified (harvested, no recorded run)
luogen1996/MCN/model/garan.py
code served (permissive licence) · get_code("5d597490de9d1f49")
How it ran

no invocation recorded.

normalize_by_dim Not yet run
unverified (harvested, no recorded run)
luogen1996/MCN/model/utils.py
code served (permissive licence) · get_code("364718e6449b4023")
How it ran

no invocation recorded.

simple_fusion Not yet run
unverified (harvested, no recorded run)
luogen1996/MCN/model/mcn_model.py
code served (permissive licence) · get_code("b0d7842e5e5a7f8d")
How it ran

no invocation recorded.

up_proj_cat_proj Not yet run
unverified (harvested, no recorded run)
luogen1996/MCN/model/mcn_model.py
code served (permissive licence) · get_code("daccc76ced7a707b")
How it ran

no invocation recorded.

update_from_dict Not yet run
unverified (harvested, no recorded run)
luogen1996/MCN/utils/parse_config.py
code served (permissive licence) · get_code("c7ed0cfdeeed82ac")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 6 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 5 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
letterbox_image 3 other papers
2 dated earlier, 1 later
1804.02767 (2018-04)
YOLOv3: An Incremental Improvement
1905.05055 (2019-05)
Object Detection in 20 Years: A Survey
2601.07576 (2026-01)
A Multimodal Dataset of Student Oral Presentations with Sensors and Evaluation Data
rand 3 other papers
2 dated earlier, 1 later
1804.02767 (2018-04)
YOLOv3: An Incremental Improvement
1905.05055 (2019-05)
Object Detection in 20 Years: A Survey
2601.07576 (2026-01)
A Multimodal Dataset of Student Oral Presentations with Sensors and Evaluation Data
expand_and_tile 1 other paper
1 later
2210.15871 (2022-10)
VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
expand_and_tile_1 1 other paper
1 later
2210.15871 (2022-10)
VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
get_checkpoint_paths 1 other paper
1 dated earlier
1902.00751 (2019-02)
Parameter-Efficient Transfer Learning for NLP
normalize_by_dim 1 other paper
1 later
2210.15871 (2022-10)
VLT: Vision-Language Transformer and Query Generation for Referring Segmentation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Referring expression comprehension (REC) and segmentation (RES) are two highly-related tasks, which both aim at identifying the referent according to a natural language expression. In this paper, we propose a novel Multi-task Collaborative Network (MCN) to achieve a joint learning of REC and RES for the first time. In MCN, RES can help REC to achieve better language-vision alignment, while REC can help RES to better locate the referent. In addition, we address a key challenge in this multi-task setup, i.e., the prediction conflict, with two innovative designs namely, Consistency Energy Maximization (CEM) and Adaptive Soft Non-Located Suppression (ASNLS). Specifically, CEM enables REC and RES to focus on similar visual regions by maximizing the consistency energy between two tasks. ASNLS supresses the response of unrelated regions in RES based on the prediction of REC. To validate our model, we conduct extensive experiments on three benchmark datasets of REC and RES, i.e., RefCOCO, RefCOCO+ and RefCOCOg. The experimental results report the significant performance gains of MCN over all existing methods, i.e., up to +7.13% for REC and +11.50% for RES over SOTA, which well confirm the validity of our model for joint REC and RES learning.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2003.08813")
get_code_for_paper("2003.08813")
have("2003.08813")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2003.08813.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2003.08813.svg)](https://syntology.ai/paper/2003.08813)

Connect an agent — have() is free.